Sensitivity analysis of the results of the management model SUE (State University System) based on data envelopment analysis
Main Article Content
The Colombian State University System (SUE) has used a mathematical model for evaluating public universities, sorting them according to their performance. However, it is necessary to propose a different approach for various disagreements with the results. To respond to these complaints, the DEA research group at the Technological University of Pereira proposed an alternative model (Soto & Arenas, 2005) based on Data Envelopment Analysis (DEA), which provides a method for calculating the performance of the Colombian SUE. Conventional DEA does not directly include the ability to assess the sensitivity of efficiency to changes in information. Having a measure of how far a set of Decision Making Units, (DMUs), retains its level of efficiency due to variations in the information is fundamental for the evaluation of the robustness of the results. This article proposes to use the approach of Sensitivity Analysis for DEA models with simultaneous changes in all the information, developed by (Seiford & Zhu, 1998), to measure the sensitivity of the model results for the SUE. Initially, some of the reasons to analyze the sensitivity of the model will be discussed. Then, the chosen methodology and the model are described. Finally the results and conclusions will be presented.
1.
Amariles JM, Soto-Mejía JA. Sensitivity analysis of the results of the management model SUE (State University System) based on data envelopment analysis. inycomp [Internet]. 2015 Jul. 31 [cited 2024 Nov. 5];17(2):53-64. Available from: https://revistaingenieria.univalle.edu.co/index.php/ingenieria_y_competitividad/article/view/2188
Authors grant the journal and Universidad del Valle the economic rights over accepted manuscripts, but may make any reuse they deem appropriate for professional, educational, academic or scientific reasons, in accordance with the terms of the license granted by the journal to all its articles.
Articles will be published under the Creative Commons 4.0 BY-NC-SA licence (Attribution-NonCommercial-ShareAlike).